Paper page - From Synthesis to Removal: Physics-Grounded Reflection Simulation and Diffusion-Based Video Dereflection

Source: https://huggingface.co/papers/2608.11562 Published on Aug 12

·

Submitted byhttps://huggingface.co/HigherHu

Higheron Aug 13

Abstract

A closed-loop framework combining physics-based video synthesis, diffusion-based video dereflection, and a new benchmark achieves state-of-the-art video reflection removal with fast inference.

Videos captured through glass often contain reflections that degrade visual quality and interfere with downstream vision tasks. Although single-image reflection removal has been extensively studied, video reflection removal remains largely underexplored due to the lack of paired video data, temporally coherent removal models, and dedicated evaluation benchmarks. We present a closed-loop framework that unifiesphysics-grounded reflection simulation,diffusion-based video dereflection, and benchmark evaluation. OurS2R-Synthesispipeline generates paired reflected and reflection-free videos by performing physics-grounded augmentation in the structure space and rendering realistic reflected videos with a trainedvideo diffusion renderer; the augmentation models key glass-related effects including roughness-induced blur, thickness-induced ghosting, and reflectance variation. Based on the synthesized data, we introduceS2R-Removal, the first diffusion-based video reflection removal model, which adapts a pretrained video diffusion prior throughreflection-aware latent adaptationandone-step pixel-geometric refinement, recovering the clean transmission in a single denoising step. We further buildS2R-Bench, the first benchmark for video reflection removal, supporting both full-reference evaluation and real-world human perceptual assessment. Experiments onS2R-Benchand multiple public image benchmarks demonstrate state-of-the-art performance and faster inference than even non-diffusion baselines, and validate the effectiveness ofS2R-Synthesis. Project page: https://codingwzp.github.io/VideoDereflection_S2R.

View arXiv pageView PDFProject pageAdd to collection

Get this paper in your agent:

hf papers read 2608\.11562

Don’t have the latest CLI?curl \-LsSf https://hf\.co/cli/install\.sh \| bash

Models citing this paper0

No model linking this paper

Cite arxiv.org/abs/2608.11562 in a model README.md to link it from this page.

Datasets citing this paper0

No dataset linking this paper

Cite arxiv.org/abs/2608.11562 in a dataset README.md to link it from this page.

Spaces citing this paper0

No Space linking this paper

Cite arxiv.org/abs/2608.11562 in a Space README.md to link it from this page.

Collections including this paper0

No Collection including this paper

Add this paper to acollectionto link it from this page.